Prediction of Weld Strength in Power Ultrasonic Spot Welding Process Using Artificial Neural Network (ANN) and Back Propagation Method

In this presented work, the employment of artificial neural network (ANN) connected with back propagation method was performed to predict the strength of joining materials that carried out by using ultrasonic spot welding process. The models which created in this study were investigated and their process parameters were analysed. These parameters were classified and set as input variables like for example applying pressure, time of duration weld and trigger of vibrating amplitude while weld strength of joining dissimilar materials (Al-Cu) is set as output parameters. The identification from the process parameters are obtained using number of experiments and finite element analyses based prediction. The results of actual and numerical are accurate and reliability, however its complexity has significant effect due to sensitive to the condition variation of welding processes. Therefore, the needed for an efficient technique like artificial neural network coupled with back propagation method is required to use the experiments as an input data in simulation of ultrasonic welding process, finding the adequacy of modeling process in prediction of weld strength and to confirm the performance of using mathematical methods. The results of the selecting non-linear models show a noticeable potency when using ANN with back propagation method in providing high accuracy compared with other results obtained by conventional models.